Image processor and image processing system including the same

Abstract

Disclosed is an image processor and an image processing system including the same, and the image processor may include a first pre-processor configured to generate a first point cloud based on a sparse depth map, a first post-processor configured to model a surface of the sparse depth map based on the first point cloud, a second pre-processor configured to generate a difference frame corresponding to a difference between a previous frame and a current frame, a second post-processor configured to generate a second point cloud of a dimension corresponding to the sparse depth map, based on the difference frame, and a generator configured to generate a dense depth map using the second point cloud and the modeled surface.

What is claimed is: 
     
         1 . An image processor comprising:
 a first pre-processor configured to generate a first point cloud based on a sparse depth map;   a first post-processor configured to model a surface of the sparse depth map based on the first point cloud;   a second pre-processor configured to generate a difference frame corresponding to a difference between a previous frame and a current frame;   a second post-processor configured to generate a second point cloud of a dimension corresponding to the sparse depth map, based on the difference frame; and   a generator configured to generate a dense depth map using the second point cloud and the modeled surface.   
     
     
         2 . The image processor of  claim 1 , wherein the previous frame and the current frame are generated and provided consecutively from a same image sensor. 
     
     
         3 . The image processor of  claim 1 , wherein the first pre-processor generates a specific area, which overlaps a field of view corresponding to the current frame in the sparse depth map, as the first point cloud. 
     
     
         4 . The image processor of  claim 1 , wherein the first post-processor includes:
 a clustering component configured to cluster the first point cloud for each subject; and   a modeling component configured to generate the modeled surface by adding virtual points to each point set clustered for each subject.   
     
     
         5 . The image processor of  claim 4 , wherein the clustering component uses a convex hull algorithm or a Delaunay triangulation algorithm. 
     
     
         6 . The image processor of  claim 1 , wherein the second post-processor uses ray casting. 
     
     
         7 . The image processor of  claim 1 , wherein the generator includes:
 an estimator configured to estimate dense depth information using the second point cloud and the modeled surface; and   an output component configured to generate the dense depth map based on the dense depth information and the sparse depth map.   
     
     
         8 . The image processor of  claim 7 , wherein the estimator estimates depth values of intersections between the second point cloud and the modeled surface as the dense depth information,
 wherein the estimator calculates the depth values using barycentric coordinates.   
     
     
         9 . The image processor of  claim 7 , wherein the output component performs a depth correction operation when generating the dense depth map,
 wherein the depth correction operation includes at least one of depth expansion and depth hole filling.   
     
     
         10 . An image processing system comprising:
 a depth information generator configured to generate a sparse depth map;   an image generator configured to generate a previous frame and a current frame; and   an image processor configured to generate a difference frame corresponding to a difference between the previous frame and the current frame, and generate a dense depth map based on the difference frame and the sparse depth map.   
     
     
         11 . The image processing system of  claim 10 , wherein the image generator consecutively generates the previous frame and the current frame, and provides the image processor with the previous frame and the current frame. 
     
     
         12 . The image processing system of  claim 10 , wherein the image processor includes:
 a modeler configured to model a surface of the sparse depth map based on the sparse depth map;   a converter configured to convert the difference frame into a second point cloud having a dimension corresponding to the sparse depth map, based on the previous frame and the current frame; and   a generator configured to generate the dense depth map using the second point cloud and the modeled surface.   
     
     
         13 . The image processing system of  claim 12 , wherein the modeler includes:
 a first pre-processor configured to generate a first point cloud based on the sparse depth map; and   a first post-processor configured to generate the modeled surface based on the first point cloud.   
     
     
         14 . The image processing system of  claim 13 , wherein the first pre-processor generates a specific area, which overlaps a field of view corresponding to the current frame in the sparse depth map, as the first point cloud. 
     
     
         15 . The image processing system of  claim 13 , wherein the first post-processor includes:
 a clustering component configured to cluster the first point cloud for each subject; and   a modeling component configured to generate the modeled surface by adding virtual points to each point set clustered for each subject.   
     
     
         16 . The image processing system of  claim 12 , wherein the converter includes:
 a second pre-processor configured to generate the difference frame based on the previous frame and the current frame; and   a second post-processor configured to generate the second point cloud based on the difference frame.   
     
     
         17 . The image processing system of  claim 12 , wherein the generator includes:
 an estimator configured to estimate dense depth information using the second point cloud and the modeled surface; and   an output component configured to generate the dense depth map based on the dense depth information and the sparse depth map.   
     
     
         18 . The image processing system of  claim 17 , wherein the estimator estimates depth values of intersections between the second point cloud and the modeled surface as the dense depth information. 
     
     
         19 . The image processing system of  claim 17 , wherein the output component performs a depth correction operation when generating the dense depth map, and the depth correction operation includes at least one of depth expansion and depth hole filling. 
     
     
         20 . A method of operating an image processor, the method comprising:
 generating a first point cloud based on a sparse depth map;   modeling a surface of the sparse depth map based on the first point cloud;   generating a difference frame corresponding to a difference between a previous frame and a current frame;   generating a second point cloud of a dimension corresponding to the sparse depth map, based on the difference frame; and   generating a dense depth map using the second point cloud and the modeled surface.